Image retrieval process of fruits and flowers with CBIR concept was represented by the colors and shapes using adaptive histogram method for color, and invariant moment for shape. To measure the similarity between the query image and the basis data image Euclidean distance function was used, where the result is f (x). Calculations for f (y) through the process of 'fuzzy-ing'-S curve, where the value of f (x) guides the sigmoid function. The value f(y) on each image than the threshold value based image query. Basically, the algorithm displays the image based on Threshold features, by comparing the threshold value with the value f(y). A high grade value (approaching 1) indicates that the feature of the sample (query) image is similar to the basis data image, and vice versa. The process was continued by comparing the value grades of the image representation of color and form using min operator in fuzzy logic, so that it only displayed several images that have some resemblances in accordance with the original image. The advantage of threshold algorithm and the fuzzy function-compared to other methods-lies in the simplicity method in the image retrieval, so that the performance of CBIR becomes more reliable and effective. ABSTRAK Proses temu kembali citra buah dan bunga dengan konsep CBIR direpresentasi dengan warna dan bentuk mengunakan metode Adaptive Histogram untuk warna, dan invariant moment untuk bentuk. Untuk mengukur kemiripan antara citra query dan citra basis data digunakan fungsi jarak Euclid, di mana hasilnya sebagai f(x). Perhitungan untuk f (y) melalui proses fuzzy-fikasi pada kurva-S, di mana nilai f(x) menjadi pedoman dalam menjalankan fungsi sigmoid. Nilai f(y) pada setiap citra dibandingkan berdasarkan nilai ambang citra query. Pada dasarnya, algoritma Threshold menampilkan citra berdasarkan cirinya, dengan membandingkan nilai ambang dengan nilai f(y). Nilai grade tinggi (mendekati 1) menunjukkan bahwa ciri citra contoh (query) mirip dengan citra basis data, begitu juga sebaliknya. Proses dilanjutkan dengan membandingkan nilai grade representasi citra warna dan bentuk mengunakan operator min pada logika fuzzy, sehingga ditampilkan beberapa citra saja yang mempunyai kemiripan sesuai dengan citra asli. Kelebihan algoritma Threshold dan fungsi fuzzy ini, dibandingkan dengan metode lainnya terletak pada simplisitas metode dalam temu kembali citra, sehingga kinerja CBIR menjadi lebih andal dan efektif.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.